Line Plot from Scientific Research

The training loss function, <L_n^{simple}> , against iterations for DM-1c. Here, < ⋅ > represents the average over a batch of training data, each of which has a corresponding random step n with 0 ≤ n ≤ N . The inset presents the fourth-order flatness obtained from DM-1c at different iterations (A: 10 x 10^3, B: 30 x 10^3 C: 250 x 10^3 ), in comparison with that from DNS data. Statistics and error bars are derived as in Fig. 4.

DOI